Creator
StepFun
Released
2026-02-02
Intelligence
25.5
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.10
input tokens
Out $/1M
$0.30
output tokens
Blended $/1M
$0.15
3:1 blended
Speed
0
tokens / sec
Profile
License, openness, and modality — the governance layer.
License
Apache 2.0
commercial OK
Weights
Open
downloadable
Modalities
Image · Text
Parameters
196B
total
Step-3.5-Flash is StepFun's fast, cost-effective text model optimized for quick inference. Built on their Step3 architecture, it offers strong performance across text tasks with low latency and efficient token usage, ideal for production workloads requiring speed and cost efficiency.
Capability profile
Category strength across 20 domains, via LLM Stats.
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
Providers
Inference hosts serving this model — their own pricing and measured performance, cheapest input first.
| Provider | In $/1M | Out $/1M | Throughput | Latency | Status |
|---|---|---|---|---|---|
| StepFun | $0.10 | $0.40 | 150 | 0.30 | active |
1 host · via LLM Stats